Video Extractor Pro

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 2:46 AM UTC
• Version: 1.0.2

Overview

This is a local video frame and clip extraction skill that matches its stated purpose and shows no hidden network, credential, persistence, or destructive behavior.

Install only if you are comfortable using a Chinese-language local ffmpeg helper. Process videos you have permission to use, choose output paths carefully because ffmpeg is invoked with overwrite behavior, and treat extracted frames, clips, GIFs, and metadata as potentially sensitive.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (8)

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: All user-facing descriptive text and trigger phrases are written in Chinese, with no indication that other languages are supported or that the user can choose their preferred language. This can violate a language/locale policy when a skill imposes a single language without explicit opt-in or justification.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger phrases are generic video-related commands such as '视频截图' and '截取视频', with no scoping to a specific workflow, consent boundary, or file-selection step. This can cause unintended invocation in broader conversations about videos, leading the agent to process media or generate derived outputs when the user did not clearly intend to activate this skill.

Natural-Language Policy Violations

Medium

• Confidence: 97% confidence
• Finding: This code file contains natural-language strings and help text that force a specific language for descriptions and command output. Under the policy, a language/locale constraint should either be optional for the user or clearly justified as region-specific; neither is present here.

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

def run_ffmpeg(cmd):
    """执行 ffmpeg 命令"""
    print(f"执行: {' '.join(cmd)}")
    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode != 0:
        print(f"错误: {result.stderr}")
        return False

• Confidence: 70% confidence
• Finding: subprocess module calls execute external commands. Without careful input validation, this enables command injection.

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

def run_ffmpeg(cmd):
    """执行 ffmpeg 命令"""
    print(f"执行: {' '.join(cmd)}")
    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode != 0:
        print(f"错误: {result.stderr}")
        return False

• Confidence: 70% confidence
• Finding: subprocess module calls execute external commands. Without careful input validation, this enables command injection.

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

def run_ffmpeg(cmd):
    """执行 ffmpeg 命令"""
    print(f"执行: {' '.join(cmd)}")
    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode != 0:
        print(f"错误: {result.stderr}")
        return False

• Confidence: 70% confidence
• Finding: subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Missing User Warnings

Low

• Confidence: 76% confidence
• Finding: The documentation describes extracting frames, clips, and GIFs from videos but provides no warning that videos may contain sensitive, copyrighted, or private content and that extracted outputs may create additional exposure. In a content-analysis or review context, derived media can increase privacy and data-handling risk if users are not alerted before processing.

Natural-Language Policy Violations

Low

• Confidence: 93% confidence
• Finding: The manifest description, command labels, tags, and keywords are written only in Chinese, with no indication that the skill supports other languages or that it is intentionally limited to a Chinese-speaking audience. This can violate a language/locale policy when users are not given a choice or the restriction is not documented as region-specific.

Static analysis

No suspicious patterns detected.